# 🎙️ SenseVoice Streaming ASR
[](https://pypi.org/project/sense-voice-streaming-asr/)
[](https://pypi.org/project/sense-voice-streaming-asr/)
[](LICENSE)
A lightweight, real-time streaming speech recognition engine powered by SenseVoiceSmall.
## ✨ Features
- **Streaming ASR**: lightweight, real-time streaming speech recognition engine, runs on CPU with realtime recongnition.
- **Integrated VAD**: Built-in Voice Activity Detection (VAD) to detect speech segments.
- **Multilingual**: Supports `Chinese`, `English`, `Japanese`, `Korean`, `Cantonese` out of the box.
- **Self-contained**: Models bundled inside the package — no external downloads needed.
- **Pure Python + ONNX**: No heavy dependencies; runs on CPU.
## 🚀 Installation
```bash
pip install sense-voice-streaming-asr
```
> Requires Python ≥ 3.8.
## 🛠️ Development
To install in development mode:
```bash
git clone https://github.com/yourname/sense-voice-streaming-asr.git
cd sense-voice-streaming-asr
git submodule init # for SenseVoice models
pip install -e .
```
## 📄 License
Apache 2.0 License.
This project incorporates code from [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) which is licensed under Apache 2.0. The project as a whole is therefore distributed under the Apache 2.0 license. See the [LICENSE](LICENSE) file for full license text.
## 🙏 Acknowledgements
- [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) by FunAudioLLM
- [SenseVoice ONNX Models](https://www.modelscope.cn/models/iic/SenseVoiceSmall)
- [FSMN VAD](https://www.modelscope.cn/iic/speech_fsmn_vad_zh-cn-16k-common-onnx)
- [Kaldi-native-fbank](https://github.com/csukuangfj/kaldi-native-fbank)
- ONNX Runtime
Raw data
{
"_id": null,
"home_page": null,
"name": "sense-voice-streaming-asr",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "nikoseven <nikoseven@outlook.com>",
"keywords": "speech-recognition, asr, streaming, real-time, sensevoice, multilingual, chinese, english, japanese, korean, cantonese, voice-processing, audio-processing, artificial-intelligence, machine-learning",
"author": null,
"author_email": "nikoseven <nikoseven@outlook.com>",
"download_url": "https://files.pythonhosted.org/packages/74/20/baeae93891a1694ac59a89dbd6b01439de4c15de1fa3122eea614a31058b/sense_voice_streaming_asr-0.1.1.tar.gz",
"platform": null,
"description": "# \ud83c\udf99\ufe0f SenseVoice Streaming ASR\n\n[](https://pypi.org/project/sense-voice-streaming-asr/)\n[](https://pypi.org/project/sense-voice-streaming-asr/)\n[](LICENSE)\n\nA lightweight, real-time streaming speech recognition engine powered by SenseVoiceSmall.\n\n\n## \u2728 Features\n\n- **Streaming ASR**: lightweight, real-time streaming speech recognition engine, runs on CPU with realtime recongnition.\n- **Integrated VAD**: Built-in Voice Activity Detection (VAD) to detect speech segments.\n- **Multilingual**: Supports `Chinese`, `English`, `Japanese`, `Korean`, `Cantonese` out of the box.\n- **Self-contained**: Models bundled inside the package \u2014 no external downloads needed.\n- **Pure Python + ONNX**: No heavy dependencies; runs on CPU.\n\n## \ud83d\ude80 Installation\n\n```bash\npip install sense-voice-streaming-asr\n```\n\n> Requires Python \u2265 3.8.\n\n\n\n## \ud83d\udee0\ufe0f Development\n\nTo install in development mode:\n\n```bash\ngit clone https://github.com/yourname/sense-voice-streaming-asr.git\ncd sense-voice-streaming-asr\ngit submodule init # for SenseVoice models\npip install -e .\n```\n\n\n## \ud83d\udcc4 License\n\nApache 2.0 License.\n\nThis project incorporates code from [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) which is licensed under Apache 2.0. The project as a whole is therefore distributed under the Apache 2.0 license. See the [LICENSE](LICENSE) file for full license text.\n\n## \ud83d\ude4f Acknowledgements\n\n- [SenseVoice](https://github.com/FunAudioLLM/SenseVoice) by FunAudioLLM\n- [SenseVoice ONNX Models](https://www.modelscope.cn/models/iic/SenseVoiceSmall)\n- [FSMN VAD](https://www.modelscope.cn/iic/speech_fsmn_vad_zh-cn-16k-common-onnx)\n- [Kaldi-native-fbank](https://github.com/csukuangfj/kaldi-native-fbank)\n- ONNX Runtime\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Real-time streaming automatic speech recognition (ASR) with support for Chinese, English, Cantonese, Japanese, and Korean languages using SenseVoiceSmall model.",
"version": "0.1.1",
"project_urls": {
"Bug Tracker": "https://github.com/nikoseven/sense-voice-streaming-asr/issues",
"Documentation": "https://github.com/nikoseven/sense-voice-streaming-asr#readme",
"Homepage": "https://github.com/nikoseven/sense-voice-streaming-asr",
"Repository": "https://github.com/nikoseven/sense-voice-streaming-asr"
},
"split_keywords": [
"speech-recognition",
" asr",
" streaming",
" real-time",
" sensevoice",
" multilingual",
" chinese",
" english",
" japanese",
" korean",
" cantonese",
" voice-processing",
" audio-processing",
" artificial-intelligence",
" machine-learning"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "efdf5576f1a88399e6b4d39ad5f18da9b27f1c39671ccbfed864f03cccc8a3b3",
"md5": "445bddf006eca5f8bd87bbf2749e5b90",
"sha256": "8078c7446bba5161a2f6e924bdec3d58cabab7a30b077558a2ed97b1ffa0b3a2"
},
"downloads": -1,
"filename": "sense_voice_streaming_asr-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "445bddf006eca5f8bd87bbf2749e5b90",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 116528,
"upload_time": "2025-10-08T16:46:08",
"upload_time_iso_8601": "2025-10-08T16:46:08.108889Z",
"url": "https://files.pythonhosted.org/packages/ef/df/5576f1a88399e6b4d39ad5f18da9b27f1c39671ccbfed864f03cccc8a3b3/sense_voice_streaming_asr-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7420baeae93891a1694ac59a89dbd6b01439de4c15de1fa3122eea614a31058b",
"md5": "eba278fdd2b80d59af92a6de4ac25884",
"sha256": "321e2f8c5cabd165c7796a1ee3e20d7448c554abfb367ea50d0d2efa24c5e135"
},
"downloads": -1,
"filename": "sense_voice_streaming_asr-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "eba278fdd2b80d59af92a6de4ac25884",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 111934,
"upload_time": "2025-10-08T16:46:09",
"upload_time_iso_8601": "2025-10-08T16:46:09.409605Z",
"url": "https://files.pythonhosted.org/packages/74/20/baeae93891a1694ac59a89dbd6b01439de4c15de1fa3122eea614a31058b/sense_voice_streaming_asr-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-10-08 16:46:09",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "nikoseven",
"github_project": "sense-voice-streaming-asr",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "sense-voice-streaming-asr"
}
JSON
